@byunghwee.bsky.social
Reposted
Large language models can map the complex landscape of human beliefs by analyzing online debates, enabling quantitative analysis of belief polarization and cognitive dissonance. doi.org/g9n6m4
LLMs delve into online debates to create a detailed map of human beliefs
Large language models (LLMs), such as the model underpinning the functioning of the well-known conversational platform ChatGPT, have proved to be very promising for summarizing and generating written texts.
phys.org
June 22, 2025 at 1:02 PM
Large language models can map the complex landscape of human beliefs by analyzing online debates, enabling quantitative analysis of belief polarization and cognitive dissonance. doi.org/g9n6m4
Reposted
A semantic embedding space based on large language models for modelling human beliefs www.nature.com/articles/s41...
A semantic embedding space based on large language models for modelling human beliefs - Nature Human Behaviour
Lee et al. fine-tune large language models on debate data to create belief embeddings that capture the nuanced relationships between a wide range of beliefs, thus offering insight into how people form...
www.nature.com
June 4, 2025 at 2:56 PM
A semantic embedding space based on large language models for modelling human beliefs www.nature.com/articles/s41...
📢 Exciting news! Our two-year project at Indiana University has just been published in Nature Human Behaviour!
🔗 doi.org/10.1038/s415...
In this study, we used large language models and a massive online debate dataset to map over 100,000 human beliefs into a "belief space."
In this study, we used large language models and a massive online debate dataset to map over 100,000 human beliefs into a "belief space."
A semantic embedding space based on large language models for modelling human beliefs - Nature Human Behaviour
Lee et al. fine-tune large language models on debate data to create belief embeddings that capture the nuanced relationships between a wide range of beliefs, thus offering insight into how people form...
doi.org
June 5, 2025 at 11:34 AM
📢 Exciting news! Our two-year project at Indiana University has just been published in Nature Human Behaviour!
🔗 doi.org/10.1038/s415...
In this study, we used large language models and a massive online debate dataset to map over 100,000 human beliefs into a "belief space."
In this study, we used large language models and a massive online debate dataset to map over 100,000 human beliefs into a "belief space."
Reposted
In this Article, Lee et al. fine tune large language models on debate data to create belief embeddings that capture the nuanced relationship between a wide range of topics and reveal how people form new opinions.
A semantic embedding space based on large language models for modelling human beliefs - Nature Human Behaviour
Lee et al. fine-tune large language models on debate data to create belief embeddings that capture the nuanced relationships between a wide range of beliefs, thus offering insight into how people form new beliefs.
www.nature.com
June 4, 2025 at 2:48 PM
In this Article, Lee et al. fine tune large language models on debate data to create belief embeddings that capture the nuanced relationship between a wide range of topics and reveal how people form new opinions.